Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications

Documenti analoghi

• Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
  di: Kopaničáková, Alena, et al.
  Pubblicazione: (2023)
• A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers
  di: Lee, Youngkyu, et al.
  Pubblicazione: (2025)
• Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
  di: Lapucci, Matteo, et al.
  Pubblicazione: (2024)
• Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models
  di: Lapucci, Matteo, et al.
  Pubblicazione: (2024)
• Moments, Time-Inversion and Source Identification for the Heat Equation
  di: Liu, Kang, et al.
  Pubblicazione: (2025)